LM-Infinite: Simple On-the-Fly Length Generalization for Large Language Models
#1
by
cognisant
- opened
This seems like a good repo (Given the large context window) to mention this paper: https://huggingface.co/papers/2308.16137
I haven't seen it implemented yet but it doesn't require retraining. Wondering your thoughts.
@cognisant any release model or code repo regards to that paper so far? No code no real.